Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    date

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bero
    -0.06
    armor
    -0.06
    Trademark
    -0.06
    Ст
    -0.06
    uples
    -0.05
    includes
    -0.05
    (pointer
    -0.05
    _secure
    -0.05
     Pastor
    -0.05
    aturdays
    -0.05
    POSITIVE LOGITS
     repl
    0.07
    pla
    0.07
     inexp
    0.07
    共和
    0.07
     Compar
    0.07
    leaning
    0.07
     guide
    0.07
    شی
    0.07
    дя
    0.06
     loosen
    0.06
    Act Density 0.001%

    No Known Activations